# Speech Emotion Recognition on MSP-IMPROV (6-fold session-independent cross-validation) Source: [Speech Emotion Recognition on MSP-IMPROV (6-fold session-independent cross-validation)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:45.333Z Evaluation of Speech Emotion Recognition performance on the MSP-IMPROV dataset using 6-fold session-independent cross-validation, reporting Weighted Accuracy (WA) and Unweighted Accuracy (UA). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Speech Emotion Recognition | | Dataset (including any stated split) | MSP-IMPROV (6-fold session-independent cross-validation) | | Metric | Weighted Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Weighted Accuracy](): Higher is better; unit: PERCENT. - [Unweighted Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Weighted Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Proposed Method | 58.55 | Not recorded | 69326756d6b0dd3342934562 | | Liu et al. \[31\] | 55.8 | Not recorded | 69326756d6b0dd3342934562 | | Liu et al. \[30\] | 51.51 | Not recorded | 69326756d6b0dd3342934562 | | Cao et al. \[29\] | 50.7 | Not recorded | 69326756d6b0dd3342934562 | | Xu et al. \[28\] | 47.9 | Not recorded | 69326756d6b0dd3342934562 | | Nediyanchath et al. \[27\] | 47.3 | Not recorded | 69326756d6b0dd3342934562 | | Guo et al. \[26\] | 46.2 | Not recorded | 69326756d6b0dd3342934562 | ### Proposed Method Weighted Accuracy: 58.55. Result ID: 699a0f205698665ec492a8f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Liu et al. \[31\] Weighted Accuracy: 55.8. Result ID: 699a0f205698665ec492a8f8. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Liu et al. \[30\] Weighted Accuracy: 51.51. Result ID: 699a0f205698665ec492a8f7. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Cao et al. \[29\] Weighted Accuracy: 50.7. Result ID: 699a0f205698665ec492a8f6. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Xu et al. \[28\] Weighted Accuracy: 47.9. Result ID: 699a0f205698665ec492a8f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Nediyanchath et al. \[27\] Weighted Accuracy: 47.3. Result ID: 699a0f205698665ec492a8f4. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. ### Guo et al. \[26\] Weighted Accuracy: 46.2. Result ID: 699a0f205698665ec492a8f3. [Reporting paper]() Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.